Papers › RWKV-CLIP: A Robust Vision-Language Representation Learner

RWKV-CLIP: A Robust Vision-Language Representation Learner

11 Jun 2024arXiv:2406.06973archive 2025-07-28

Tiancheng Gu, Kaicheng Yang, Xiang An, Ziyong Feng, Dongnan Liu, Weidong Cai, Jiankang Deng

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the perspectives of data and model architecture. To address the prevalence of noisy data and enhance the quality of large-scale image-text data crawled from the internet, we introduce a diverse description generation framework that can leverage Large Language Models (LLMs) to synthesize and refine content from web-based texts, synthetic captions, and detection tags. Furthermore, we propose RWKV-CLIP, the first RWKV-driven vision-language representation learning model that combines the effective parallel training of transformers with the efficient inference of RNNs. Comprehensive experiments across various model scales and pre-training datasets demonstrate that RWKV-CLIP is a robust and efficient vision-language representation learner, it achieves state-of-the-art performance in several downstream tasks, including linear probe, zero-shot classification, and zero-shot image-text retrieval. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/RWKV-CLIP

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2406.06973")

Code

Syntology Ran 7 of 14 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

deepglint/rwkv-clip officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 7 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
1ran · fixture could not drive it
3ran
7unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from deepglint/RWKV-CLIP. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

basic_clean deepglint/RWKV-CLIP/model/open_clip/tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 98f385d847636a3e · report
drop_path deepglint/RWKV-CLIP/model/utils_vision_rwkv/drop.py official repository ran · fixture could not drive it MIT (permissive) · 87577b3ff9d32712 · report
get_pairs deepglint/RWKV-CLIP/model/open_clip/tokenizer.py official repository ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report
image_transform deepglint/RWKV-CLIP/model/open_clip/transform.py official repository ran MIT (permissive) · ff9bfb497bc486af · report
load_model_configs deepglint/RWKV-CLIP/model_config/utils_notebook.py official repository ran MIT (permissive) · 59b9fe12dfcd73e5 · report
load_model_weight deepglint/RWKV-CLIP/model/utils.py official repository ran MIT (permissive) · f159f1ed836af624 · report
whitespace_clean deepglint/RWKV-CLIP/model/open_clip/tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9542161e9640b858 · report
WarperCLIP_V_T_RWKV_method deepglint/RWKV-CLIP/model/utils.py official repository unverified MIT (permissive) · 4a3350dc35016870 · report
WarperCLIP_V_T_RWKV_text_change_head deepglint/RWKV-CLIP/model/utils.py official repository unverified MIT (permissive) · cd7722094b3b2370 · report
compute_retrieval deepglint/RWKV-CLIP/text_image_retrieval.py official repository unverified MIT (permissive) · 4d278aa7e3a2f51e · report
create_dali_pipeline deepglint/RWKV-CLIP/dataloaders/imagenet.py official repository unverified MIT (permissive) · 9da98aebf2dd1b3a · report
gather_features deepglint/RWKV-CLIP/loss.py official repository unverified MIT (permissive) · ddcbd45e940484ee · report
generate_init_weight_V6 deepglint/RWKV-CLIP/model/Text_rwkv.py official repository unverified MIT (permissive) · f9b03b79fff32f11 · report
get_image_feature deepglint/RWKV-CLIP/text_image_retrieval.py official repository unverified MIT (permissive) · 5eaaaa9625688979 · report

Tasks

Image-text RetrievalRepresentation LearningText RetrievalZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections